📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: 📜 Paper: 🛠️ Code and weights: 🧵Details in thread... (1/n)

🔸Proteina is a novel flow-based protein backbone generative model. It uses an alpha carbon backbone representation, is trained with flow matching, relies on a scalable and efficient transformer network, and offers hierarchical fold class conditioning for enhanced control. (2/n)

🔸We train on synthetic datasets of up to 21M protein structures curated from the AlphaFold Database (left plot). Further, we condition Proteina on hierarchical C.A.T.H protein structure classification labels (right plot), with a tailored classifier-free guidance scheme. (3/n)

🔸The fold class conditioning provides fine control during generation and allows us to guide with respect to high-level secondary structure content or low-level specific fold classes. The method can also be used to enhance the amount of beta sheets in a controlled manner. (4/n)

🔸Proteina uses an efficient and scalable non-equivariant transformer network with up to 400M parameters. We minimize the use of computationally expensive and memory-consuming layers such as triangle attention, allowing Proteina to generate backbones of up to 800 residues. (5/n)

🔸Quantitatively, Proteina achieves state-of-the-art designable and diverse protein backbone generation (unconditional or fold class-conditional). In particular at long lengths, it significantly outperforms previous models, which cannot generate proteins at this scale. (6/n)

🔸Proteina also outperforms previous models on motif-scaffolding, where a functionally relevant motif is given and the model is tasked with generating a viable supporting scaffold. Below, we show quantitative evaluations for the benchmark introduced by RFDiffusion. (7/n)

🔸Protein structure generation performance is often measured in terms of designability, diversity and novelty. Drawing inspiration from image generation, we explore three complementary metrics that analyze models at the distribution level, providing additional insights. (8/n)

🔸We also demonstrate LoRA-based fine-tuning on a smaller set of high-quality protein structures from the PDB, and we show that autoguidance, where the model is guided by a weaker version of itself, can be used to boost designability. See our paper for details. (9/n)

🔸Proteina is a fantastic collaboration with a team of wonderful colleagues at NVIDIA: 🔥 @tomasgeffner *, @DidiKieran *, @Oxer22 *, Danny Reidenbach, @ZhonglinJC , @json_yim , @mario1geiger , @sacdallago , Emine Kucukbenli , @ArashVahdat , @karsten_kreis * 🔥 (10/n)

🔸Check out our project page ( our paper ( and our code ( 🔥 We released 8 sets of weights, for all experiments, for you to play with! 🔥 Enjoy! And see you at ICLR'25! 😀 (11/11)

📢 The Draft Plan for HUDI’s Relaunch: 🌐 HUDI goes multichain 🛸 Mega airdrop 🔥 Token burn 🔥 🤖 Product launch: HUDI AI to talk with your data and beyond 💡 What do you think? Suggestions or ideas? 🐸 Let’s make HUDI great again! 🚀 #HUDI #Crypto #binance #token #bitmart #bnb #token #launch #AirdropAlert